INDEX

Explanations

technical terms and numerical data related to studies or analyses

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

RenderAtEndOf

-1.36

 EconPapers

-1.25

richTextPanel

-1.20

tagHelperRunner

-1.12

 Paglinawan

-1.07

setVerticalGroup

-1.05

__':

-1.03

Билгалдахарш

-0.97

TypedDataSet

-0.96

featureID

-0.96

POSITIVE LOGITS

↵

0.55

0.45

0.42

0.41

↵↵

0.41

0.40

<b>

0.39

<eos>

0.39

Activations Density 0.719%

technical terms and numerical data related to studies or analyses

No Comments

No Known Activations